% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Galchenkova:632810,
      author       = {Galchenkova, Marina and Tolstikova, A. and Oberthuer, D.
                      and Sprenger, J. and Brehm, Wolfgang and White, T. A. and
                      Barty, Anton and Chapman, H. N. and Yefanov, Oleksandr},
      title        = {{C}ompression and data reduction in serial crystallography},
      issn         = {2053-2733},
      reportid     = {PUBDB-2025-02235},
      year         = {2023},
      abstract     = {Protein crystallography is one of the most successful
                      methods for biological structure determination. This
                      technique requires many diffraction snapshots to get 3D
                      structural information of the studied protein. Even more
                      patterns are needed for studying fast protein dynamics that
                      can be achieved using serial crystallography (SX).
                      Fortunately, new X-ray facilities such as 4th generation
                      synchrotrons and Free Electron Lasers (FELs) combined with
                      newly developed X-ray detectors opened a way to carry out
                      these experiments at a rate of more than 1000 images per
                      second. The drawback of this increase in acquisition rate is
                      the volume of collected data - up to 2 PB of data per
                      experiment could be easily obtained. Therefore, new data
                      reduction strategies have to be developed and deployed.
                      Lossless data reduction methods will not change the data,
                      but usually fail to achieve a high compression ratio. On the
                      other hand, lossy compression methods can significantly
                      reduce the amount of data, but they require careful
                      evaluation of the resulting data quality. We have tested
                      different approaches for both lossless and lossy compression
                      applied to SX data, proposed some new ways for lossy
                      compression and demonstrated appropriate methods for data
                      quality assessment. By checking the resulting statistics of
                      compressed data (like CC*/Rsplit, Rfree/Rwork) we have
                      demonstrated that the volume of the measured data can be
                      greatly reduced (10-100 times!) while the quality of the
                      resulting data was kept almost constant. In addition, we
                      tested lossy compression methods on the SAD dataset
                      (thaumatin collected at 4.57 keV, measured at the SwissFEL)
                      and demonstrated that even such very sensitive data can be
                      successfully compressed. It allowed us to determine the
                      limit of application for all considered lossy compressions.
                      Some of the proposed compression strategies, tested on SX
                      and MX datasets, can be used for other types of experiments,
                      even with different sources (for example electron and
                      neutron diffraction).},
      month         = {Aug},
      date          = {2023-08-22},
      organization  = {Twenty-Sixth Congress and General
                       Assembly of the International Union of
                       Crystallography, Melbourne (Australia),
                       22 Aug 2023 - 29 Aug 2023},
      cin          = {FS-CFEL-1-BMX / CFEL-I / FS-SC},
      ddc          = {530},
      cid          = {I:(DE-H253)FS-CFEL-1-BMX-20210408 /
                      I:(DE-H253)CFEL-I-20161114 / I:(DE-H253)FS-SC-20210408},
      pnm          = {633 - Life Sciences – Building Blocks of Life: Structure
                      and Function (POF4-633) / AIM, DFG project
                      G:(GEPRIS)390715994 - EXC 2056: CUI: Advanced Imaging of
                      Matter (390715994)},
      pid          = {G:(DE-HGF)POF4-633 / G:(GEPRIS)390715994},
      experiment   = {EXP:(DE-H253)P-P11-20150101},
      typ          = {PUB:(DE-HGF)1},
      doi          = {10.1107/S2053273323095244},
      url          = {https://bib-pubdb1.desy.de/record/632810},
}